Cover Image

Enhancing the Stability of LLM-based Speech Generation Systems through Self-Supervised Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Martín-Cortinas, Álvaro, Sáez-Trigueros, Daniel, Vallés-Pérez, Iván, Tura-Vecino, Biel, Biliński, Piotr, Lajszczak, Mateusz, Beringer, Grzegorz, Barra-Chicote, Roberto, Lorenzo-Trueba, Jaime
Format:	Preprint
Published:	2024
Subjects:	Audio and Speech Processing Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Investigating self-supervised features for expressive, multilingual voice conversion
by: Martín-Cortinas, Álvaro, et al.
Published: (2025)

SCRAPS: Speech Contrastive Representations of Acoustic and Phonetic Spaces
by: Vallés-Pérez, Ivan, et al.
Published: (2023)

Universal Semantic Disentangled Privacy-preserving Speech Representation Learning
by: Vecino, Biel Tura, et al.
Published: (2025)

Lightweight End-to-end Text-to-speech Synthesis for low resource on-device applications
by: Vecino, Biel Tura, et al.
Published: (2025)

Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations
by: Guo, Xin, et al.
Published: (2026)

Cyclostationarity Analysis as a Complement to Self-Supervised Representations for Speech Deepfake Detection
by: Hanilçi, Cemal, et al.
Published: (2026)

BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
by: Łajszczak, Mateusz, et al.
Published: (2024)

Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
by: Chorowski, Jan, et al.
Published: (2021)

k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning
by: Yang, Yifan, et al.
Published: (2024)

Refining Self-Supervised Learnt Speech Representation using Brain Activations
by: Li, Hengyu, et al.
Published: (2024)

Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge
by: Liu, Rui, et al.
Published: (2024)

Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment
by: Stahl, Benjamin, et al.
Published: (2025)

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs
by: Tseng, Wei-Cheng, et al.
Published: (2025)

Augmenting Polish Automatic Speech Recognition System With Synthetic Data
by: Bondaruk, Łukasz, et al.
Published: (2024)

A Large-Scale Probing Analysis of Speaker-Specific Attributes in Self-Supervised Speech Representations
by: Chiu, Aemon Yat Fei, et al.
Published: (2025)

Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations
by: Aihara, Ryo, et al.
Published: (2025)

Weakly Supervised Phonological Features for Pathological Speech Analysis
by: Thienpondt, Jenthe, et al.
Published: (2025)

Rethinking Mamba in Speech Processing by Self-Supervised Models
by: Zhang, Xiangyu, et al.
Published: (2024)

Semi-Supervised Contrastive Learning of Musical Representations
by: Guinot, Julien, et al.
Published: (2024)

Investigation of Speech and Noise Latent Representations in Single-channel VAE-based Speech Enhancement
by: Li, Jiatong, et al.
Published: (2025)

Generic Speech Enhancement with Self-Supervised Representation Space Loss
by: Sato, Hiroshi, et al.
Published: (2025)

Spoken Language Corpora Augmentation with Domain-Specific Voice-Cloned Speech
by: Czyżnikiewicz, Mateusz, et al.
Published: (2024)

Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations
by: Li, Jialu, et al.
Published: (2024)

Augmenting Open-Vocabulary Dysarthric Speech Assessment with Human Perceptual Supervision
by: Jia, Kaimeng, et al.
Published: (2025)

Large Language Model Guided Decoding for Self-Supervised Speech Recognition
by: Cohen, Eyal, et al.
Published: (2025)

Multi-Distillation from Speech and Music Representation Models
by: Wei, Jui-Chiang, et al.
Published: (2025)

Leveraging Content and Acoustic Representations for Speech Emotion Recognition
by: Dutta, Soumya, et al.
Published: (2024)

HYFuse: Aligning Heterogeneous Speech Pre-Trained Representations in Hyperbolic Space for Speech Emotion Recognition
by: Phukan, Orchid Chetia, et al.
Published: (2025)

Enhanced Reverberation as Supervision for Unsupervised Speech Separation
by: Saijo, Kohei, et al.
Published: (2024)

Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models
by: C, Shiva Kumar, et al.
Published: (2025)

Prosody as Supervision: Bridging the Non-Verbal--Verbal for Multilingual Speech Emotion Recognition
by: Girish, et al.
Published: (2026)

The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning
by: Vaessen, Nik, et al.
Published: (2024)

Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?
by: Osakuade, Opeyemi, et al.
Published: (2024)

On the Use of Self-Supervised Representation Learning for Speaker Diarization and Separation
by: Baroudi, Séverin, et al.
Published: (2025)

TTA: Transcribe, Translate and Alignment for Cross-lingual Speech Representation
by: Liu, Wei, et al.
Published: (2025)

Learning Time-Graph Frequency Representation for Monaural Speech Enhancement
by: Wang, Tingting, et al.
Published: (2025)

ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals
by: E, Ameenudeen P, et al.
Published: (2026)

SLASH: Self-Supervised Speech Pitch Estimation Leveraging DSP-derived Absolute Pitch
by: Terashima, Ryo, et al.
Published: (2025)

Comparing Unsupervised and Supervised Semantic Speech Tokens: A Case Study of Child ASR
by: Shi, Mohan, et al.
Published: (2025)

SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech
by: Lin, Jingru, et al.
Published: (2024)